INDEX

Explanations

phrases related to disabilities and the inclusion of individuals with disabilities in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agua

-0.14

egin

-0.14

QRS

-0.14

actics

-0.14

enberg

-0.13

amak

-0.13

 culpa

-0.13

eniz

-0.13

ê°ľë¥¼

-0.13

 taper

-0.13

POSITIVE LOGITS

 intellectual

0.39

 disabilities

0.37

 Intellectual

0.34

 developmental

0.32

 learning

0.32

 cognitive

0.30

 physical

0.28

 mental

0.28

 Down

0.26

 Learning

0.26

Activations Density 0.049%

phrases related to disabilities and the inclusion of individuals with disabilities in various contexts

No Comments

No Known Activations